CN110458340B - Building air conditioner cold load autoregressive prediction method based on mode classification - Google Patents
Building air conditioner cold load autoregressive prediction method based on mode classification Download PDFInfo
- Publication number
- CN110458340B CN110458340B CN201910675653.2A CN201910675653A CN110458340B CN 110458340 B CN110458340 B CN 110458340B CN 201910675653 A CN201910675653 A CN 201910675653A CN 110458340 B CN110458340 B CN 110458340B
- Authority
- CN
- China
- Prior art keywords
- load
- prediction
- air conditioner
- day
- building air
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000007621 cluster analysis Methods 0.000 claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000010219 correlation analysis Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000001816 cooling Methods 0.000 abstract description 29
- 238000004378 air conditioning Methods 0.000 abstract description 12
- 238000004458 analytical method Methods 0.000 abstract description 5
- 238000011160 research Methods 0.000 abstract description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 9
- 230000000694 effects Effects 0.000 description 5
- 238000010438 heat treatment Methods 0.000 description 4
- 238000005057 refrigeration Methods 0.000 description 4
- 238000009423 ventilation Methods 0.000 description 4
- 238000003064 k means clustering Methods 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000000498 cooling water Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Pure & Applied Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Optimization (AREA)
- Operations Research (AREA)
- Mathematical Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Algebra (AREA)
- Water Supply & Treatment (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses a building air conditioner cold load autoregressive prediction method based on pattern classification. Can be applied to scientific research and engineering application in the related fields of building air conditioning systems. The method comprises the following steps: preprocessing the input data of all models to obtain an original data set; performing cluster analysis on the air conditioner load, namely pre-classifying load modes; determining influence factors of two time scale prediction models before and on the same day, and determining input selection of the prediction models before and on the same day; checking the correlation between the cold load and the influencing factors by adopting a spearman correlation coefficient analysis method; determining a load pattern of a predicted day; and finally, establishing a daily cooling load prediction model and a daily cooling load prediction model. The prediction method can improve the accuracy of the prediction result of the cold load of the building air conditioner, accelerate the calculation speed of the prediction model and guide the operation regulation of the building air conditioning system.
Description
Technical Field
The invention relates to a method for predicting the cold load of a building air conditioner, in particular to an autoregressive prediction method for the cold load of the building air conditioner based on pattern classification.
Background
Many studies have shown that the energy consumed by heating, ventilation and air conditioning (HVAC) systems is a major component of the total energy consumption of a building. Most of current air conditioning systems adopt a traditional feedback control method, and the system is adjusted based on the backwater temperature of a user side. However, due to the complex building structure, the behaviors of people are changeable, and the feedback control cannot meet the demands of people. By predicting the building's cooling load for a period of time in the future, changes in indoor conditions can be responded in real time, and therefore, cooling load prediction is an effective way to improve the energy efficiency of the air conditioning system. The prediction of the cold load can inform operators of future refrigeration demands in advance, the operators can manage and set the system according to the predicted cold load, and the regulation of the heating ventilation air conditioning system is changed from a feedback mode to a feed-forward mode. Predictive models for guiding system management and operation can be broadly divided into day-ahead and day-ahead. The day-ahead predictive model is used to determine the next day's cooling load. The system can guide operators to make management plans of the heating ventilation air conditioning system in advance, such as arranging a water chilling unit, predicting a water pump and a cooling tower used on a daily basis, and maintaining or repairing other equipment. The daily prediction model is used for determining the cold load of the prediction time of several hours in the future, can accurately predict the refrigeration requirement in a period of time, and guides operators to formulate the operation strategy of the heating, ventilation and air conditioning system.
The autoregressive model uses historical data to simulate predicted future data in each period before the same variable, and assumes that the predicted future data are in a linear relationship, and the historic data comprise an endogenous variable hysteresis term. The ARX model is an autoregressive model with external input, and the model is added with the external input on the basis of the autoregressive model and is more in accordance with the data characteristics of the cold load. In the previous research, the ARX model is commonly used for directly predicting the building cold load, and the historical data and related parameters required for predicting the cold load at different times are different, so that the calculation result of the ARX model also has larger error.
Therefore, a reasonable method is adopted to establish a building air conditioner cold load autoregressive prediction method based on pattern classification, which is a key problem to be solved urgently in reasonably managing and setting the system and reducing the energy consumption of the system.
Disclosure of Invention
In view of the above, the present invention provides a method for autoregressive prediction of cooling load of building air conditioner based on pattern classification to solve the above-mentioned problems.
Based on the prior invention, the invention carries out the following improvements: preprocessing data by adopting a quarter bit distance method, detecting abnormal values in building original data, and obtaining an original data set; carrying out load pattern cluster analysis by adopting k-means cluster analysis to obtain a load pattern typical day; determining factors influencing the day-ahead prediction and the day-ahead prediction, performing correlation analysis on the cold load of the building air conditioner and the influencing factors by adopting a Styleman coefficient analysis method, removing variables with lower correlation, and obtaining model input choices of the day-ahead and the day-ahead prediction models; determining a load mode of a predicted day by adopting k-means cluster analysis; and establishing a daily cooling load prediction model and a daily cooling load prediction model by adopting an autoregressive model based on pattern classification.
The invention provides a building air conditioner cold load autoregressive prediction method based on pattern classification, which comprises the following steps:
preprocessing data by adopting a quarter bit distance method, detecting abnormal values in building original data, and obtaining an original data set;
classifying the building cold load by adopting k-means cluster analysis, and carrying out load mode cluster analysis to obtain a load mode typical day;
determining factors influencing the day-ahead prediction and the day-ahead prediction, performing correlation analysis on the building air conditioner cold load and the influencing factors, removing variables with lower correlation, and obtaining model input choices of the day-ahead and the day-ahead prediction models;
determining a load mode of a predicted day by adopting k-means cluster analysis;
adopting an autoregressive model based on mode classification to establish a daily cooling load prediction model and a current daily cooling load prediction model;
and evaluating the building air conditioner cold load prediction model.
Further, the influencing factors include influencing the daily cooling load prediction factor and influencing the current daily cooling load prediction factor.
Further, all data are preprocessed, and the adopted method is a quarter bit method.
Further, the load mode cluster analysis is carried out on the building cold load, and the adopted method is a k-means clustering method. Firstly, randomly selecting k objects as initial clustering centers; secondly, calculating the distance between each object and each sub-cluster center, and distributing each object to the cluster center closest to the object; then, calculating a new cluster center; finally, the above two steps are repeated until the sum of the squares of the errors is locally minimal.
The calculation formula of the error square sum is
Wherein: SSE represents the sum of squares of errors;
C i representing clusters S i Is a cluster center of the group (C);
k represents the number of clustering centers;
x represents cluster S i Is included.
The load day closest to each cluster center will be considered the typical day.
Further, correlation analysis is carried out on the cold load of the building air conditioner and influence factors, and the magnitude and the direction of correlation of various variables are calculated by adopting the spearman coefficient.
The method for calculating the spearman coefficient is
Wherein: n represents the number of data;
d i representing the difference in ordering of the two variables in the ith data.
When selecting the influencing factor, the following selection criteria are followed, and the correlation coefficient of the influencing factor is compared with a defined limit value. When the limit value is satisfied, it is considered to have a significant effect on the predicted load, which is then extracted as a model input. There is no unified way to select limit values; the user should select the limit value appropriately according to the application. However, the general requirement for the limit value is greater than 0.5, which indicates that there is at least a relationship between them.
One sample representing a variable; one sample representing a variable; the number of samples representing the sum of the variables. Further, a load pattern of the predicted day is determined using k-means cluster analysis.
Furthermore, an autoregressive model based on mode classification is adopted to establish a daily cooling load prediction model and a daily cooling load prediction model.
An autoregressive model (ARX model) based on pattern classification is used to describe the relationship between the predicted cold load and various model inputs, the selected model inputs being the parameters of strongest relevance to the cold load obtained by the Szechwan coefficient method.
The beneficial effects are that: the prediction method can improve the accuracy of the prediction result of the cold load of the building air conditioner, accelerate the calculation speed of the prediction model and guide the operation regulation of the building air conditioning system.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a load pattern clustering result.
Detailed Description
The present invention will be further described in detail below with reference to specific embodiments and with reference to the accompanying drawings, in order to make the objects, technical solutions and advantages of the present invention more apparent. As shown in fig. 1, the present embodiment provides a method for predicting a cooling load model based on an autoregressive model and an artificial neural network model with additional inputs, comprising the steps of:
step 1: preprocessing data by adopting a quarter bit distance method, detecting abnormal values in building original data, and obtaining an original data set;
a building air conditioning system is operated 24 hours a day. The air conditioning system of the building consists of 8 water chilling units with the same specification. The rated refrigerating capacity of the 1 water chilling unit is 4186 kilowatts. The cooling tower, the cooling water pump and the primary side chilled water pump in the air conditioning system are matched with the water chiller one by one. The secondary side chilled water pump is adjusted according to the air conditioner terminal. The outlet temperature and the water quantity of the chilled water are rated design values. The actual cold supply data of the building are measured by a calorimeter, the outdoor dry bulb temperature data are measured by a weather station, and the data recording intervals are all 1 hour. Detailed embodiments of the present invention are based on the cooling capacity data records of the building in two cooling seasons of 2017 and 2018.
Step 2: classifying the building cold load by adopting a k-means clustering method, and carrying out load pattern clustering analysis to obtain a load pattern typical day;
firstly, randomly selecting k objects as initial clustering centers; secondly, calculating the distance between each object and each sub-cluster center, and distributing each object to the cluster center closest to the object; then, calculating a new cluster center; finally, the above two steps are repeated until the sum of the squares of the errors is locally minimal. The calculation formula of the error square sum is shown in formula (1).
Wherein: SSE represents the sum of squares of errors;
C i representing clusters S i Is a cluster center of the group (C);
k represents the number of clustering centers;
x represents cluster S i Data points in (a); the load day closest to each cluster center will be considered the typical day.
The refrigeration loads per hour in 2017 and 2018 were clustered based on a K-means clustering method. The number of clusters is determined by the sum of squares of the errors, and as the number of clusters increases to 5, the reduction of SSE slows down as shown in figure 2. Therefore, five load modes are set in the cooling season of two years.
Step 3: determining factors influencing the day-ahead prediction and the day-ahead prediction, performing correlation analysis on the building air conditioner cold load and the influencing factors, removing variables with lower correlation, and obtaining model input choices of the day-ahead and the day-ahead prediction models;
and carrying out correlation analysis on the cold load and influence factors of the building air conditioner, and calculating the magnitude and direction of the correlation of various variables by adopting a spearman coefficient. The method for calculating the spearman coefficient is shown in the formula (2).
Wherein: n represents the number of data;
d i representing the difference in ordering of the two variables in the ith data.
When selecting the influencing factor, the following selection criteria are followed, and the correlation coefficient of the influencing factor is compared with a defined limit value. When the limit value is satisfied, it is considered to have a significant effect on the predicted load, which is then extracted as a model input. There is no unified way to select limit values; the limits should be reasonably selected according to the application. However, the limit value is generally required to be greater than 0.5, which indicates that there is at least a relationship between them.
In the same load mode, the relation between the historical data load and the predicted daily load is determined through correlation analysis. In the case of the case construction, taking cluster 5 as an example, the load of t-24 and t-48 was found to have the strongest correlation with the predicted load when the limit value of the correlation coefficient was 0.4. Thus, the loads of T-24 and T-48 are entered as models of the cluster 5 day old predictive model. For clusters 2 through 4, the same analysis is performed to obtain model inputs. For cluster 1, where there is little refrigeration demand throughout the day, when the predicted day is determined to be cluster 1, the hour load for that day is considered zero, and thus no correlation analysis is performed.
One sample representing a variable; one sample representing a variable; the number of samples representing the sum of the variables. Due to the thermal inertia of the building envelope, a certain hysteresis occurs in the trend of the outdoor dry bulb temperature transfer to the inside. The historical period outdoor dry bulb temperature also has an effect on the predicted load. Through correlation analysis, the relation between the cold load of the predicted time t and the outdoor dry bulb temperature of the predicted time and the historical time is determined. The effect of outdoor dry bulb temperature on predicted load is the same in all load modes. Therefore, the relationship between the predicted load and the outdoor dry bulb temperature was analyzed using the data of the entire cooling season.
Step 4, determining a load mode of a prediction day by adopting k-means cluster analysis;
firstly, randomly selecting k objects as initial clustering centers; secondly, calculating the distance between each object and each sub-cluster center, and distributing each object to the cluster center closest to the object; then, calculating a new cluster center; finally, the above two steps are repeated until the sum of the squares of the errors is locally minimal. The calculation formula of the error square sum is shown in formula (3).
Wherein: SSE represents the sum of squares of errors;
C i representing clusters S i Is a cluster center of the group (C);
k represents the number of clustering centers;
x represents cluster S i Is included.
All load days of the 2017 and 2018 cooling seasons were randomly divided into 10 data sets. The load day in each dataset is distributed throughout all phases of the cooling season, and each dataset contains five load patterns, so model verification is generic. The classification results are shown in Table 1.
TABLE 1 k-means cluster analysis results
Table 1 shows that SSE accuracy varies from 0.5 to 0.9, with an average classification accuracy of about 0.7. From all the data sets, the data set with higher classification accuracy (data set 7) and the data set with lower classification accuracy (data set 9) are selected for subsequent analysis.
an autoregressive model (ARX model) with additional inputs is used to describe the relationship between the predicted cooling load and the various model inputs, in this case the selected input parameters are outdoor dry bulb temperature and historical cooling load, using the method shown in equation (4).
Wherein: q (Q) t A cooling load representing a predicted time t;
T i indicating the outdoor dry bulb temperature;
Q i representing historical cooling load;
m represents the influence Q t The number of outdoor dry bulb temperature values;
w i coefficients representing model inputs
w l A constant offset factor is represented for partially reducing the effect of modeling errors.
ARX prediction techniques are used to build a daily predictive model of data clusters 7 and 9. Taking data cluster 7 as an example, table 2 gives the ARX predictive model for cluster 2-cluster 5.
Table 2 ARX prediction model for clusters 2 through 5
Although the invention has been described above with reference to the accompanying drawings, the invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many modifications may be made by those of ordinary skill in the art without departing from the spirit of the invention, which fall within the protection of the invention.
Claims (2)
1. The autoregressive prediction method for the cold load of the building air conditioner based on the pattern classification is characterized by comprising the following steps of:
(1) Preprocessing data by adopting a quarter bit distance method, and detecting abnormal values in building original data;
(2) Classifying the building air conditioner cold load obtained in the step (1) by adopting k-means cluster analysis, and carrying out cluster analysis of load modes to obtain a load mode of a typical day;
(3) Determining factors influencing the day-ahead prediction and the day-ahead prediction, performing correlation analysis on the building air conditioner cold load and the influencing factors, removing variables with lower correlation, and obtaining model input choices of the day-ahead and the day-ahead prediction models;
(4) Determining a load mode of a predicted day by adopting k-means cluster analysis;
(5) According to the load mode obtained in the step (4), an autoregressive model is adopted to establish a prediction model of the air conditioner cold load before and at the same time;
the influence factors comprise a prediction factor for influencing the daily cold load and a prediction factor for influencing the daily cold load;
the method adopted in the step (2) for carrying out load pattern cluster analysis on the building air conditioner load and determining the load pattern of the predicted day in the step (4) is k-means cluster analysis:
firstly, randomly selecting k objects as initial clustering centers;
secondly, calculating the distance between each object and each sub-cluster center, and distributing each object to the cluster center closest to the object;
then, calculating a new cluster center;
finally, repeating the two steps until the square sum of errors is locally minimum, wherein the calculation formula of the square sum of errors is as follows:
wherein: SSE represents the sum of squares of errors;
C i representing clusters S i Is a cluster center of the group (C);
k represents the number of clustering centers;
x represents cluster S i Data points in (a);
the load day closest to each cluster center will be considered the typical day;
in the step (3), correlation analysis is carried out on the cold load of the building air conditioner and influence factors, and the magnitude and the direction of correlation of various variables are calculated by adopting a spearman correlation coefficient:
wherein: n represents the number of data;
d i representing the difference in ordering of the two variables in the ith data.
2. The method for autoregressive prediction of building air conditioner cold load based on pattern classification according to claim 1, wherein in the step (5), an autoregressive model based on pattern classification is used to build a model for predicting the building air conditioner cold load before and on the same day.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910675653.2A CN110458340B (en) | 2019-07-25 | 2019-07-25 | Building air conditioner cold load autoregressive prediction method based on mode classification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910675653.2A CN110458340B (en) | 2019-07-25 | 2019-07-25 | Building air conditioner cold load autoregressive prediction method based on mode classification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110458340A CN110458340A (en) | 2019-11-15 |
| CN110458340B true CN110458340B (en) | 2023-06-02 |
Family
ID=68483424
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910675653.2A Active CN110458340B (en) | 2019-07-25 | 2019-07-25 | Building air conditioner cold load autoregressive prediction method based on mode classification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110458340B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111612031A (en) * | 2020-04-03 | 2020-09-01 | 华电电力科学研究院有限公司 | Regional building dynamic load prediction method based on high-dimensional spatial clustering neighbor search |
| CN111401658B (en) * | 2020-04-08 | 2022-07-19 | 西安建筑科技大学 | Parallel cold load prediction method based on building space unit |
| CN111583059B (en) * | 2020-04-20 | 2024-01-23 | 上海电力大学 | Distributed energy station typical daily load acquisition method based on k-means clustering |
| CN112215474B (en) * | 2020-09-18 | 2024-06-21 | 上海市建筑科学研究院有限公司 | Running characteristic model for water chilling unit |
| CN114688692B (en) * | 2020-12-30 | 2023-10-20 | 北京天诚同创电气有限公司 | Load prediction method, system and device |
| CN112862222A (en) * | 2021-03-26 | 2021-05-28 | 中国建设银行股份有限公司 | Air conditioner return air temperature prediction method, abnormality monitoring method and related device |
| CN113094907A (en) * | 2021-04-15 | 2021-07-09 | 天津大学 | Combined scheduling method for air conditioner load and electric vehicle charging load |
| CN113869601A (en) * | 2021-10-18 | 2021-12-31 | 深圳供电局有限公司 | Power consumer load prediction method, device and equipment |
| CN115130899B (en) * | 2022-07-18 | 2023-04-18 | 东南大学溧阳研究院 | Kmeas-GM-based air conditioner load day-ahead response capacity evaluation method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009110379A (en) * | 2007-10-31 | 2009-05-21 | Nippon Telegr & Teleph Corp <Ntt> | Pattern prediction unit, pattern prediction method, and pattern prediction program |
| CN107704875A (en) * | 2017-09-30 | 2018-02-16 | 山东建筑大学 | Based on the building load Forecasting Methodology and device for improving IHCMAC neutral nets |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103699771B (en) * | 2013-09-27 | 2016-09-21 | 广东工业大学 | A kind of sight-clustering method of cooling load prediction |
| CN105761163A (en) * | 2016-02-22 | 2016-07-13 | 国家电网公司 | Temperature adjustment load quantifying method based on correlation analysis and meteorological factor clustering |
| CN107203822A (en) * | 2016-03-16 | 2017-09-26 | 上海吉贝克信息技术有限公司 | Method and system based on the Logistic security customers attrition predictions returned |
| CN106127360A (en) * | 2016-06-06 | 2016-11-16 | 国网天津市电力公司 | A kind of multi-model load forecasting method analyzed based on user personality |
| CN106682764A (en) * | 2016-12-02 | 2017-05-17 | 河海大学 | Method for predicting other day air-conditioning load of public building based on parallel prediction strategy |
-
2019
- 2019-07-25 CN CN201910675653.2A patent/CN110458340B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009110379A (en) * | 2007-10-31 | 2009-05-21 | Nippon Telegr & Teleph Corp <Ntt> | Pattern prediction unit, pattern prediction method, and pattern prediction program |
| CN107704875A (en) * | 2017-09-30 | 2018-02-16 | 山东建筑大学 | Based on the building load Forecasting Methodology and device for improving IHCMAC neutral nets |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110458340A (en) | 2019-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110458340B (en) | Building air conditioner cold load autoregressive prediction method based on mode classification | |
| CN103912966B (en) | A kind of earth source heat pump refrigeration system optimal control method | |
| Ben-Nakhi et al. | Energy conservation in buildings through efficient A/C control using neural networks | |
| Kawashima et al. | Hourly thermal load prediction for the next 24 hours by ARIMA, EWMA, LR and an artificial neural network | |
| CN101021914A (en) | Heating ventilating and air conditioner load predicting method and system | |
| Zhang et al. | Development and evaluation of cooling load prediction models for a factory workshop | |
| Wang et al. | Energy consumption prediction for water-source heat pump system using pattern recognition-based algorithms | |
| Kreider et al. | Predicting hourly building energy usage | |
| CN117439101B (en) | Intelligent network for interaction of new energy and flexible load in power grid | |
| CN113959071B (en) | Centralized water chilling unit air conditioning system operation control optimization method based on machine learning assistance | |
| CN114046593A (en) | Dynamic predictive machine learning type air conditioner energy-saving control method and system | |
| CN111723085B (en) | Method and system for cleaning electric energy consumption data of public building air conditioner | |
| CN115696871B (en) | Data center water cooling system regulation and control method and device based on machine learning | |
| CN113778215A (en) | Method for realizing data center PUE prediction and consumption reduction strategy based on big data | |
| CN112686442A (en) | Air conditioner tail end energy consumption prediction method and system based on operation diversity | |
| CN108346009A (en) | A kind of power generation configuration method and device based on user model self study | |
| CN111680712A (en) | Transformer oil temperature prediction method, device and system based on similar moments in the day | |
| CN112329813B (en) | Energy consumption prediction feature extraction method and system | |
| CN117454168A (en) | Building energy consumption prediction method and system | |
| CN115327930B (en) | Visual energy-saving control method and system | |
| CN112781183A (en) | Intelligent consumption reduction method and system for air conditioning system and air conditioner | |
| CN116307074A (en) | Method for acquiring real thermal data, system and method for constructing neural network model of thermal data, and method for predicting thermal load | |
| CN114636212A (en) | GRNN-based multi-chiller system operation control method | |
| CN115271168A (en) | Method and device for predicting response potential of electrical load and storage medium | |
| CN104751233A (en) | Contract capacity optimization system and optimization method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |